Loading video...

Video Failed to Load

Go Home

A 27B parameter model used to need a server room. Now it runs on: • iPhone • Android • Mac PrismML's Bonsai makes it possible. • 1-bit weights • 27B params in just 3.9GB • ~90% of full precision quality (PrismML evals) • Better than the 2-bit version at...

RunAnywhereAI's profile picture

RunAnywhere (YC W26)

1,458 subscribers

16,421 views • 1 month ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Bonsai 27B just changed the local LLM game forever. 1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of its intelligence. That's insane. With custom WebGPU kernels written by Fable 5 and GPT 5.6 Sol, the model now runs locally in your browser!
1:29

Bonsai 27B just changed the local LLM game forever. 1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of its intelligence. That's insane. With custom WebGPU kernels written by Fable 5 and GPT 5.6 Sol, the model now runs locally in your browser!

Xenova

210,106 views • 1 month ago

The phone threshold is even harder than the storage number suggests. A phone exposes only part of its memory to an application, and the model must share that budget with its KV cache, activations, runtime, and the rest of the product. At 3.9 GB, 1-bit Bonsai 27B clears that threshold with room to work, making 27B-class local AI possible on a phone for the first time. (Demo Mode: cached & prefilled image context)
1:19

The phone threshold is even harder than the storage number suggests. A phone exposes only part of its memory to an application, and the model must share that budget with its KV cache, activations, runtime, and the rest of the product. At 3.9 GB, 1-bit Bonsai 27B clears that threshold with room to work, making 27B-class local AI possible on a phone for the first time. (Demo Mode: cached & prefilled image context)

PrismML

32,858 views • 1 month ago

PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B Hitting 89.5% of FP16 at 3.9GB. No new pretrain. No higher-precision escape hatches. No multi-GPU rig. Here's how it works. 👇 1: Codes, not floats Every weight becomes a code, with one shared FP16 scale per group of 128. Ternary is {−1, 0, +1}, binary is {−1, +1}. Sharing the scale across 128 weights keeps its cost at 16/128 = 0.125 bits. → Ternary: log2(3) + 16/128 ≈ 1.71 bits/weight → 5.9GB → Binary: 1 + 16/128 = 1.125 bits/weight → 3.9GB 2: Post-training, not from scratch No BitNet-style low-bit pretrain. It starts from off-the-shelf Qwen3.6-27B, architecture unchanged. The representation runs end to end across embeddings, attention projections, MLP projections, and the LM head. → 9.4× (ternary) and 14.2× (binary) vs the 54GB FP16 baseline 3: Labels are not bit-widths Conventional low-bit builds are mixed-precision by construction. The advertised name describes the most-compressed tensors, not the model. → Q4_K_XL, labeled "4-bit," is really 5.2 bits/weight at 17.6GB → IQ2_XXS, labeled "2-bit," is really 2.8 bits/weight at 9.4GB 4: Fitting a phone is two budgets iOS caps a single app near half of RAM, so a 12GB iPhone exposes ~6GB. The KV cache grows on top. Hybrid attention at ~75% linear means only 16 of 64 layers cache. → 4-bit KV: 4.3GB at 262K context, down from 17.2GB → 11.0 tok/s on iPhone 17 Pro Max 5: The numbers (15 benchmarks, thinking mode) → Ternary: 80.49 avg at 5.9GB — 94.6% of FP16 → 1-bit: 76.11 avg at 3.9GB — 89.5% of FP16 → IQ2_XXS falls to 57.5 on AIME26 while still scoring 88.93 on MMLU-Redux The key takeaway: 27B-class reasoning without the 54GB checkpoint — group-wise ternary and binary codes, an end-to-end low-bit language stack, 4-bit KV, on one phone. Full analysis: Repo: Model weight: Technical details: PrismML
0:37

PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B Hitting 89.5% of FP16 at 3.9GB. No new pretrain. No higher-precision escape hatches. No multi-GPU rig. Here's how it works. 👇 1: Codes, not floats Every weight becomes a code, with one shared FP16 scale per group of 128. Ternary is {−1, 0, +1}, binary is {−1, +1}. Sharing the scale across 128 weights keeps its cost at 16/128 = 0.125 bits. → Ternary: log2(3) + 16/128 ≈ 1.71 bits/weight → 5.9GB → Binary: 1 + 16/128 = 1.125 bits/weight → 3.9GB 2: Post-training, not from scratch No BitNet-style low-bit pretrain. It starts from off-the-shelf Qwen3.6-27B, architecture unchanged. The representation runs end to end across embeddings, attention projections, MLP projections, and the LM head. → 9.4× (ternary) and 14.2× (binary) vs the 54GB FP16 baseline 3: Labels are not bit-widths Conventional low-bit builds are mixed-precision by construction. The advertised name describes the most-compressed tensors, not the model. → Q4_K_XL, labeled "4-bit," is really 5.2 bits/weight at 17.6GB → IQ2_XXS, labeled "2-bit," is really 2.8 bits/weight at 9.4GB 4: Fitting a phone is two budgets iOS caps a single app near half of RAM, so a 12GB iPhone exposes ~6GB. The KV cache grows on top. Hybrid attention at ~75% linear means only 16 of 64 layers cache. → 4-bit KV: 4.3GB at 262K context, down from 17.2GB → 11.0 tok/s on iPhone 17 Pro Max 5: The numbers (15 benchmarks, thinking mode) → Ternary: 80.49 avg at 5.9GB — 94.6% of FP16 → 1-bit: 76.11 avg at 3.9GB — 89.5% of FP16 → IQ2_XXS falls to 57.5 on AIME26 while still scoring 88.93 on MMLU-Redux The key takeaway: 27B-class reasoning without the 54GB checkpoint — group-wise ternary and binary codes, an end-to-end low-bit language stack, 4-bit KV, on one phone. Full analysis: Repo: Model weight: Technical details: PrismML

Marktechpost AI

31,860 views • 1 month ago

You can now run Qwen 3.6 27B on <10GB of memory and retain 90% of the intelligence. Today, PrismML dropped Bonsai 27B - which takes their unique compression approach they have already successfully applied to Qwen3.6 8B and Flux2-Klein and applied it to a properly smart model. Here is it using an entire computer for deep research. Long horizon agentic calls already are strong with Qwen3.6 27B and they still are here - just on 10x less memory.
0:24

You can now run Qwen 3.6 27B on <10GB of memory and retain 90% of the intelligence. Today, PrismML dropped Bonsai 27B - which takes their unique compression approach they have already successfully applied to Qwen3.6 8B and Flux2-Klein and applied it to a properly smart model. Here is it using an entire computer for deep research. Long horizon agentic calls already are strong with Qwen3.6 27B and they still are here - just on 10x less memory.

Tim Carambat

62,879 views • 1 month ago

WTF?! This changes image generation forever! 🤯 PrismML just released Binary and Ternary Bonsai Image 4B! That's right, 1-bit diffusion models are here. Only ~3GB in size (FLUX.2 Klein 4B is 16GB). The most shocking part? It can run 100% locally in your browser. Try it now! 👇
0:37

WTF?! This changes image generation forever! 🤯 PrismML just released Binary and Ternary Bonsai Image 4B! That's right, 1-bit diffusion models are here. Only ~3GB in size (FLUX.2 Klein 4B is 16GB). The most shocking part? It can run 100% locally in your browser. Try it now! 👇

Xenova

182,964 views • 2 months ago

APPLE BUILT A $10,000 COMPUTER THAT RUNS WHAT USED TO REQUIRE AN ENTIRE SERVER ROOM 06:40 he shows the number that breaks everything - one Mac Studio is more powerful than four Dell or AMD machines combined and uses half the energy DeepSeek R1 doesn't run on even two competitors - you need four - one Mac Studio does it alone runs quieter than a fan in the room and uses less energy than a kettle in the kitchen four Mac Studios on a desk connected through a regular cable run a 1 trillion parameter model - what used to require an entire data center anyone can put this at home and Jeff Geerling proved it - run the same models that big companies use without cloud, without subscriptions, without data leaving the room
14:24

APPLE BUILT A $10,000 COMPUTER THAT RUNS WHAT USED TO REQUIRE AN ENTIRE SERVER ROOM 06:40 he shows the number that breaks everything - one Mac Studio is more powerful than four Dell or AMD machines combined and uses half the energy DeepSeek R1 doesn't run on even two competitors - you need four - one Mac Studio does it alone runs quieter than a fan in the room and uses less energy than a kettle in the kitchen four Mac Studios on a desk connected through a regular cable run a 1 trillion parameter model - what used to require an entire data center anyone can put this at home and Jeff Geerling proved it - run the same models that big companies use without cloud, without subscriptions, without data leaving the room

Noisy

26,153 views • 1 month ago

watch anon! 27 billion parameter model dancing at 42 tokens a second on a used rtx 3060ti, that costs 200 dollars. consuming 159 watts. temp 62 degrees. pushing almost 100% on the gpu. 6.8 of 8 gigs used with a 128k context window loaded. and every one of those spikes is the model reasoning and firing tool calls. the model is bonsai 27b at 1 bit. PrismML took qwen 3.6 27b, and crushed it to 3.9 gigabytes, about a single sign bit per weight. it drops onto an 8gb rtx 3060 ti, an ampere card from 2020, and it doesn't just load, it serves, it holds the full 128k window, it runs a hermes agent for half an hour straight, it hits its own failures and recovers, it never once drops the loop. the absurd part is the power meter. that same 27b, in its normal quant 4, wants a 24gb card and nearly 17 gigs of weights. this is it at 3.9, doing agentic work at 160 watts, on the tier people call budget. the numbers are sitting right there on nvtop, not in a slide, not a claim, the meter reading while it works. so i keep landing on one question. the model is open, apache 2.0. the card is old and cheap. the whole thing runs offline. why is almost nobody actually running this. is it the hardware, the setup, or did nobody tell you a 27b fits on the card already in your closet.
0:26

watch anon! 27 billion parameter model dancing at 42 tokens a second on a used rtx 3060ti, that costs 200 dollars. consuming 159 watts. temp 62 degrees. pushing almost 100% on the gpu. 6.8 of 8 gigs used with a 128k context window loaded. and every one of those spikes is the model reasoning and firing tool calls. the model is bonsai 27b at 1 bit. PrismML took qwen 3.6 27b, and crushed it to 3.9 gigabytes, about a single sign bit per weight. it drops onto an 8gb rtx 3060 ti, an ampere card from 2020, and it doesn't just load, it serves, it holds the full 128k window, it runs a hermes agent for half an hour straight, it hits its own failures and recovers, it never once drops the loop. the absurd part is the power meter. that same 27b, in its normal quant 4, wants a 24gb card and nearly 17 gigs of weights. this is it at 3.9, doing agentic work at 160 watts, on the tier people call budget. the numbers are sitting right there on nvtop, not in a slide, not a claim, the meter reading while it works. so i keep landing on one question. the model is open, apache 2.0. the card is old and cheap. the whole thing runs offline. why is almost nobody actually running this. is it the hardware, the setup, or did nobody tell you a 27b fits on the card already in your closet.

Sudo su

23,225 views • 25 days ago

For the first time, the latest LLMs run on the Apple Neural Engine — and NexaSDK is the only framework that makes it possible, powered by the NexaML engine. Last year, our two co-founders were invited by Apple DMLI team (Data & Machine Learning Innovation) to share their research about on-device multimodal model for local AI agents. One of the big questions in the room was: “Can the newest LLMs actually run on ANE?” At the time, nobody had a clear path. Today, that path exists. NexaSDK now runs Granite-4.0 (IBM), Qwen3 (Qwen), Gemma3 (Google), and Parakeet-v3 (NVIDIA) fully on Apple’s NPU — unlocking low-power, always-on, fast inference across Mac and iPhone. A new wave of NPU-first local AI apps is coming to Apple devices. Start with one line of code on Mac. iOS SDK coming soon.
1:42

For the first time, the latest LLMs run on the Apple Neural Engine — and NexaSDK is the only framework that makes it possible, powered by the NexaML engine. Last year, our two co-founders were invited by Apple DMLI team (Data & Machine Learning Innovation) to share their research about on-device multimodal model for local AI agents. One of the big questions in the room was: “Can the newest LLMs actually run on ANE?” At the time, nobody had a clear path. Today, that path exists. NexaSDK now runs Granite-4.0 (IBM), Qwen3 (Qwen), Gemma3 (Google), and Parakeet-v3 (NVIDIA) fully on Apple’s NPU — unlocking low-power, always-on, fast inference across Mac and iPhone. A new wave of NPU-first local AI apps is coming to Apple devices. Start with one line of code on Mac. iOS SDK coming soon.

NEXA AI

30,213 views • 9 months ago

ParoQuant just got a big upgrade 🚀 ✅ Supports the new Qwen3.5 models ⚡ Now runs on MLX (fast local inference on Apple Silicon) 🧠 Preserves reasoning quality with 4-bit quantization We also built an agent demo running locally on my 4-year-old M2 Max. Can't wait to upgrade to an M5 Max and see what kind of magic we can do. ✨
0:46

ParoQuant just got a big upgrade 🚀 ✅ Supports the new Qwen3.5 models ⚡ Now runs on MLX (fast local inference on Apple Silicon) 🧠 Preserves reasoning quality with 4-bit quantization We also built an agent demo running locally on my 4-year-old M2 Max. Can't wait to upgrade to an M5 Max and see what kind of magic we can do. ✨

Zhijian Liu

49,504 views • 5 months ago

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.
3:09

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.

QVAC

108,780 views • 5 months ago

🚀 Introducing Spaghetti Models For Free A powerful way to track possible tropical storm paths and compare forecast scenarios. With this update, you can now: - View the latest and historical model runs - Filter models to focus on the guidance you trust - See and download intensity graphs to track trends over time Stay ahead of the storm with clearer insights than ever before. Check out the latest model run for Tropical Storm Fernand here: Available now for free on: iOS: Android: Browser: And to Plus/Pro subscribers using our Windows/Mac/Linux App
0:29

🚀 Introducing Spaghetti Models For Free A powerful way to track possible tropical storm paths and compare forecast scenarios. With this update, you can now: - View the latest and historical model runs - Filter models to focus on the guidance you trust - See and download intensity graphs to track trends over time Stay ahead of the storm with clearer insights than ever before. Check out the latest model run for Tropical Storm Fernand here: Available now for free on: iOS: Android: Browser: And to Plus/Pro subscribers using our Windows/Mac/Linux App

WeatherWise.app

36,211 views • 11 months ago

VERY COOL!! Thanks jordan for the tip, I can now test my iOS app on web I asked Claude Code to set up serve-sim, a web-based iOS simulator that can stream the iOS app my Claude Code on VPS built live to me, because it's on some Mac Mini in the cloud without even a GUI (it's headless) I cannot actually try it on the Mac itself! Before Claude would make me a page with screenshots but I had no idea how the app felt, now with this it works This is hosted on the Mac Mini via SSH (it shows localhost but it's a tunnel via SSH to the Mac Mini), bit laggy but nice!
0:26

VERY COOL!! Thanks jordan for the tip, I can now test my iOS app on web I asked Claude Code to set up serve-sim, a web-based iOS simulator that can stream the iOS app my Claude Code on VPS built live to me, because it's on some Mac Mini in the cloud without even a GUI (it's headless) I cannot actually try it on the Mac itself! Before Claude would make me a page with screenshots but I had no idea how the app felt, now with this it works This is hosted on the Mac Mini via SSH (it shows localhost but it's a tunnel via SSH to the Mac Mini), bit laggy but nice!

@levelsio

426,190 views • 1 month ago

Super Mario Sunshine, running natively on macOS, iOS, and iPadOS for the first time. This is static recompilation, not a GameCube emulator. Sunshine’s PowerPC code is recompiled ahead of time into native ARM64 code. It runs locally and renders through Metal. No streaming from a Mac. ExpansionPak built DolRecomp and ModernGekko. Dolphin provides the compatibility runtime and Metal backend. I built SunPad: the Apple integration that turns that work into a real iPhone, iPad, and Mac app. On iPhone and iPad, it has full touch controls, controller support, 1×–4× internal resolution, experimental widescreen, local game import, and saves. It runs great on M2 and above iPad Pro and Apple Silicon Mac. The iPhone build is here too. Sol, Fable, and Deepseek-V4-Flash were used. Source, IPA, and full build guide below.
0:37

Super Mario Sunshine, running natively on macOS, iOS, and iPadOS for the first time. This is static recompilation, not a GameCube emulator. Sunshine’s PowerPC code is recompiled ahead of time into native ARM64 code. It runs locally and renders through Metal. No streaming from a Mac. ExpansionPak built DolRecomp and ModernGekko. Dolphin provides the compatibility runtime and Metal backend. I built SunPad: the Apple integration that turns that work into a real iPhone, iPad, and Mac app. On iPhone and iPad, it has full touch controls, controller support, 1×–4× internal resolution, experimental widescreen, local game import, and saves. It runs great on M2 and above iPad Pro and Apple Silicon Mac. The iPhone build is here too. Sol, Fable, and Deepseek-V4-Flash were used. Source, IPA, and full build guide below.

Kahris

135,759 views • 10 days ago

Ocarina of Time, running natively on iOS and iPadOS for the first time. Not an emulator. Ship of Harkinian has run on Windows, Linux, macOS, Switch, Wii U, and Android. Never iOS. Now it runs on iPad, with iPhone in the build too. The game was decompiled to C and rebuilt as a native ARM64 app rendering through Metal. No N64 hardware being simulated, no ROM interpreted at runtime, no streaming from a Mac. It isn't stuck at the N64's 240p and 20fps. Widescreen, full resolution, 60fps. This game deserves a controller, so controller support is native. Pair a Bluetooth controller and play the whole thing. Touch, keyboard, and mouse work too. I used Codex 5.6 Sol to build the iOS layer. Open sourcing it all below.
0:30

Ocarina of Time, running natively on iOS and iPadOS for the first time. Not an emulator. Ship of Harkinian has run on Windows, Linux, macOS, Switch, Wii U, and Android. Never iOS. Now it runs on iPad, with iPhone in the build too. The game was decompiled to C and rebuilt as a native ARM64 app rendering through Metal. No N64 hardware being simulated, no ROM interpreted at runtime, no streaming from a Mac. It isn't stuck at the N64's 240p and 20fps. Widescreen, full resolution, 60fps. This game deserves a controller, so controller support is native. Pair a Bluetooth controller and play the whole thing. Touch, keyboard, and mouse work too. I used Codex 5.6 Sol to build the iOS layer. Open sourcing it all below.

Kahris

1,170,793 views • 24 days ago

I’ve received complaints thar the CSD Account process on the IC Wealth app takes a long time for approval. You can download Black Star App on your Android or IPhone and get it in less than a week. Below are the steps to download it on IPhone: 1. Download TestFlight from the App Store 2. Open TestFlight after installation 3. Click this link to install BlackStar: #Stokes #Shares #GSE #Investing
1:30

I’ve received complaints thar the CSD Account process on the IC Wealth app takes a long time for approval. You can download Black Star App on your Android or IPhone and get it in less than a week. Below are the steps to download it on IPhone: 1. Download TestFlight from the App Store 2. Open TestFlight after installation 3. Click this link to install BlackStar: #Stokes #Shares #GSE #Investing

Sage Kenny 🐺🦍 | Digital Marketer

14,849 views • 6 months ago

AI researcher breaks down why your $5,000 Mac Studio runs local AI slower than benchmarks promise: "Performance isn't about the hardware - it's about three software layers stacked on top of it." in 15 minutes he tests MLX, Ollama, llama.cpp, and the new vllm-mlx head to head no GPU needed, just the Mac you probably already own - why Ollama, the most popular tool, is actually one of the slower options on Mac - the real bottleneck nobody benchmarks: 'prefill' time before the first token even appears - the exact quantization setting (4-bit) that's the best speed-to-quality tradeoff - why unified memory makes Macs uniquely good for big models compared to Nvidia GPUs complete guide to choosing the right hardware for local AI is below 👇
15:03

AI researcher breaks down why your $5,000 Mac Studio runs local AI slower than benchmarks promise: "Performance isn't about the hardware - it's about three software layers stacked on top of it." in 15 minutes he tests MLX, Ollama, llama.cpp, and the new vllm-mlx head to head no GPU needed, just the Mac you probably already own - why Ollama, the most popular tool, is actually one of the slower options on Mac - the real bottleneck nobody benchmarks: 'prefill' time before the first token even appears - the exact quantization setting (4-bit) that's the best speed-to-quality tradeoff - why unified memory makes Macs uniquely good for big models compared to Nvidia GPUs complete guide to choosing the right hardware for local AI is below 👇

rewind

207,513 views • 1 month ago

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!
4:28

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!

Kyle Hessling

24,917 views • 6 days ago

CHINESE BUSINESSMAN BOUGHT 4 MAC MINIS FOR $1,699 AND CONNECTED THEM TO HIS MACBOOK - NOW THE CORNER OF HIS DESK MAKES MORE THAN MOST OFFICES MacBook Pro 16" runs everything - assigns tasks, controls the flow, holds context - 4 Mac Minis in the corner execute inference in parallel and don't know what downtime means he connected them through EXO - an open source framework that combines multiple Apple Silicon devices into one unified cluster - and together they run models no single device could handle alone while everyone else rents cloud GPUs for $1,900/month he paid $1,699 once and the entire cluster now runs on $20/month in electricity and nothing else clients pay for inference, data never leaves the room and the cluster scales by simply placing one more Mac Mini on top the MacBook is what he works on - the Mac Minis are what work for him around the clock without days off $1,699 invested once - and a corner of a desk that makes more than most companies with a rented office
0:20

CHINESE BUSINESSMAN BOUGHT 4 MAC MINIS FOR $1,699 AND CONNECTED THEM TO HIS MACBOOK - NOW THE CORNER OF HIS DESK MAKES MORE THAN MOST OFFICES MacBook Pro 16" runs everything - assigns tasks, controls the flow, holds context - 4 Mac Minis in the corner execute inference in parallel and don't know what downtime means he connected them through EXO - an open source framework that combines multiple Apple Silicon devices into one unified cluster - and together they run models no single device could handle alone while everyone else rents cloud GPUs for $1,900/month he paid $1,699 once and the entire cluster now runs on $20/month in electricity and nothing else clients pay for inference, data never leaves the room and the cluster scales by simply placing one more Mac Mini on top the MacBook is what he works on - the Mac Minis are what work for him around the clock without days off $1,699 invested once - and a corner of a desk that makes more than most companies with a rented office

Noisy

22,391 views • 2 months ago

QVAC SDK 0.14.0 is live. This release makes the on-device stack faster on mobile, ships the developer-agent path, and takes local text-to-speech to 31 languages. Main highlights: - OpenCode and OpenClaw. The first official OpenCode plugin, plus a maintained OpenClaw compatibility path, both built on managed mode and qvac serve. Point a coding agent at a local model with far less setup and far fewer surprises. - Brain-computer interface transcription, on the SDK. Take recorded neural signal data and decode it into text, fully on-device, no cloud. Stream it in chunks through a simple API. In 0.14 it runs GPU-accelerated on iOS. - Text to Speech in 31 languages with our Supertonic3 upgrade. VOICE AND SPEECH - Supertonic3 multilingual TTS, 5 languages to 31. - Chatterbox and Supertonic now run on the Android GPU, with lower memory use (especially on iOS), quantized s3gen Chatterbox support, and a fix for Chatterbox occasionally emitting random speech. - Whisper transcription now runs on the iOS GPU. Parakeet runs on the Android GPU, with steadier real-time streaming. VISION AND OCR - VLM multi-tile batching: high-resolution Pan and Scan images are encoded in one pass instead of tile by tile, for faster vision throughput. - OCR on ggml (EasyOCR and DocTR) reaches full speed parity with the onnx path, across Metal, OpenCL, and Vulkan. PLATFORM AND RELIABILITY - Dynamic compute backends on Linux: one build picks the right backend at runtime, and opens the door to ROCm and CUDA support without per-backend builds. - Thinking tokens are kept out of the model context, so reasoning no longer fills the KV cache. SDK 0.14.0 is now leaner and faster to start. Let’s build.
1:51

QVAC SDK 0.14.0 is live. This release makes the on-device stack faster on mobile, ships the developer-agent path, and takes local text-to-speech to 31 languages. Main highlights: - OpenCode and OpenClaw. The first official OpenCode plugin, plus a maintained OpenClaw compatibility path, both built on managed mode and qvac serve. Point a coding agent at a local model with far less setup and far fewer surprises. - Brain-computer interface transcription, on the SDK. Take recorded neural signal data and decode it into text, fully on-device, no cloud. Stream it in chunks through a simple API. In 0.14 it runs GPU-accelerated on iOS. - Text to Speech in 31 languages with our Supertonic3 upgrade. VOICE AND SPEECH - Supertonic3 multilingual TTS, 5 languages to 31. - Chatterbox and Supertonic now run on the Android GPU, with lower memory use (especially on iOS), quantized s3gen Chatterbox support, and a fix for Chatterbox occasionally emitting random speech. - Whisper transcription now runs on the iOS GPU. Parakeet runs on the Android GPU, with steadier real-time streaming. VISION AND OCR - VLM multi-tile batching: high-resolution Pan and Scan images are encoded in one pass instead of tile by tile, for faster vision throughput. - OCR on ggml (EasyOCR and DocTR) reaches full speed parity with the onnx path, across Metal, OpenCL, and Vulkan. PLATFORM AND RELIABILITY - Dynamic compute backends on Linux: one build picks the right backend at runtime, and opens the door to ROCm and CUDA support without per-backend builds. - Thinking tokens are kept out of the model context, so reasoning no longer fills the KV cache. SDK 0.14.0 is now leaner and faster to start. Let’s build.

QVAC

23,973,950 views • 1 month ago

$9.3M into a pre-IPO vault in days, nearly half of first-day deposits through Mantle. Access that once ran through brokers, family offices and the right relationships now runs onchain. Hear it first from Openstock's founder f(gautham)💤 on how Mantle makes this possible ↓
0:45

$9.3M into a pre-IPO vault in days, nearly half of first-day deposits through Mantle. Access that once ran through brokers, family offices and the right relationships now runs onchain. Hear it first from Openstock's founder f(gautham)💤 on how Mantle makes this possible ↓

Mantle

14,397 views • 21 days ago